humanizer

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill explicitly instructs agents to identify and remove signs of AI-generated writing — i.e., to make AI output appear human-written — which is suspicious steering toward evading AI-authorship detection though not overtly malicious.

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires preserving every factual claim and leaves code blocks/frontmatter/data untouched when rewriting files, so if the input contains secrets (API keys, tokens, passwords) the LLM is forced to reproduce them verbatim in its output, creating an exfiltration risk.